초록 ▼

The present invention relates to deriving and utilizing content signatures. A content signature is a representation of a content item, which is derived from the content item itself. According to the invention, a method of generating a content signature for a signal is provided. The method includes t

The present invention relates to deriving and utilizing content signatures. A content signature is a representation of a content item, which is derived from the content item itself. According to the invention, a method of generating a content signature for a signal is provided. The method includes the steps of: i) dividing the signal into at least one set; ii) transforming the set into a frequency-based domain; iii) determining features of the transformed set; and iv) grouping the features so as to form a content signature of the set.

대표청구항 ▼

What is claimed is: 1. A method of linking an image or video to metadata contained in a network resource, said method comprising: receiving data corresponding to an image or video; correcting or adjusting for a geometric orientation of the data; and then calculating a fingerprint or signature as an

What is claimed is: 1. A method of linking an image or video to metadata contained in a network resource, said method comprising: receiving data corresponding to an image or video; correcting or adjusting for a geometric orientation of the data; and then calculating a fingerprint or signature as an identifier from the corrected or adjusted for data; providing at least a sub-set of the fingerprint or signature to a network resource to identify metadata associated with the image or video, wherein the metadata is associated with--but separate from--the fingerprint or signature and the data; and receiving from the network resource at least some of the metadata associated with the image or video. 2. The method of claim 1, wherein the metadata comprises at least one of a URL, image, audio or video. 3. The method of claim 1, wherein correcting or adjusting for a geometric orientation of the data comprises at least one of scaling, rotating or translating. 4. A method of linking an image to metadata contained in a network resource, said method comprising: receiving image or video data; correcting or adjusting for a geometric orientation of the image or video data; interrogating a network resource through use of a fingerprint or signature derived or determined from inherent attributes of image or video data to identify metadata associated with the image or video data, wherein the metadata is associated with--but separate from--the fingerprint or signature and the image or video data; and providing identified metadata. 5. The method of claim 4, wherein changing a geometric orientation of the data comprises at least one of scaling, rotating or translating. 6. The method of claim 4, wherein the identified metadata comprises at least one item from a group comprising: a URL, image, audio and video. 7. The method of claim 4 wherein the image or video data comprises an orientation component steganographically embedded therein, and wherein said correcting or adjusting for utilizes the orientation component. 8. The method of claim 4 wherein the inherent attributes of the changed image data comprise a plural-bit identifier. 9. The method of claim 8 wherein the plural-bit identifier is derived from the image data as at least one of a fingerprint, hash or signature. 10. A method of linking an image or video to metadata contained in a network resource comprising: receiving image or video data from a wireless device; correcting for distortion in the received image or video data; and then comparing a fingerprint or signature representing inherent characteristics of the corrected image or video data to a plurality of records, wherein each record includes at least image or video characteristics; upon a successful match with a record, identifying metadata associated with--but separate from--the fingerprint or signature and at least one of:i) the record or ii) image or video data; and providing identified metadata to the wireless device. 11. The method of claim 10, wherein the identified metadata comprises at least one of a URL, image, audio or video. 12. The method of claim 10, wherein the wireless device comprises a wireless telephone. 13. A method of linking an image or video to metadata contained in a network resource, said method comprising: receiving data corresponding to an image or video; correcting or adjusting for a geometric orientation of the data, wherein the image or video comprises an orientation component steganographically embedded therein, and wherein said correcting or adjusting for utilizes the orientation component; calculating a fingerprint or signature identifier from the data; providing at least a sub-set of the identifier to a network resource to identify metadata associated with the image or video; and receiving from the network resource at least some of the metadata associated with the image or video. 14. A method of linking media to metadata contained in a network resource, said method comprising: obtaining data corresponding to a media signal; correcting for or realigning a geometric or alignment characteristic of the data representing the media signal; and then deriving a fingerprint or signature from the corrected for or realigned data representing the media signal; interrogating a network resource with at least a sub-set of the fingerprint or signature to identify metadata associated with the media signal; and providing at least some of the identified metadata associated with the media signal. 15. The method of claim 14 wherein the media signal comprises an orientation component steganographically embedded therein, and wherein said correcting for or realigning utilizes the orientation component. 16. The method of claim 14, wherein the metadata comprises at least one of a URL, image, audio or video. 17. A method of linking media to metadata contained in a network resource, said method comprising: obtaining media; realigning or adjusting for a geometric orientation or alignment characteristic of the media; and then providing a fingerprint or signature derived or determined from inherent attributes of the media to a network resource to identify metadata associated with the media; and providing or receiving identified metadata. 18. The method of claim 17 wherein the media comprises an orientation component steganographically embedded therein, and wherein said realigning or adjusting for utilizes the orientation component. 19. The method of claim 17, wherein the metadata comprises at least one item from a group comprising: a URL, image, audio and video. 20. The method of claim 17 wherein the inherent attributes of the changed media comprise a plural-bit identifier. 21. The method of claim 20 wherein the plural-bit identifier is derived from the image data as at least one of a fingerprint hash or signature. 22. The method of claim 17 wherein the media comprises at least one of an image, video or audio 23. A method of linking media to metadata contained in a network resource, said method comprising: obtaining media; connecting for distortion in the media; and then providing a fingerprint or signature attributes calculated or derived from the corrected media to a network resource to identify metadata associated with the media; and providing or receiving identified metadata. 24. The method of claim 22 wherein the media comprises a steganographic orientation component, and said connecting utilizes the steganographic orientation component. 25. The method of claim 22 wherein the attributes comprise at least one of a hash, fingerprint or signature. 26. The method of claim 22 wherein the attributes comprise a plural-bit identifier. 27. The method of claim 25 wherein the plural-bit identifier is derived or calculated from the media as a fingerprint, hash or signature. 28. The method of claim 23 wherein the media comprises at least one of an image, video or audio.